# Image Classification on CIFAR-10 (Accuracy, Power, Delay)

Source: [Image Classification on CIFAR-10 (Accuracy, Power, Delay)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-accuracy-power-delay>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:32:38.847Z

Evaluation of Image Classification performance on the CIFAR-10 dataset, reporting standard Accuracy alongside hardware efficiency metrics such as Power consumption and inference Delay.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Image Recognition |
| Dataset (including any stated split) | CIFAR-10 |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-accuracy-power-delay.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Power](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-accuracy-power-delay.md?metric=Power>): Lower is better; unit: SCALAR.

- [Delay](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-accuracy-power-delay.md?metric=Delay>): Lower is better; unit: TIME.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SCPU | 90.6 | Not recorded | 695c96d653fdd5c36174331c |
| SiBrain (High Depth) | 90.25 | Not recorded | 695c96d653fdd5c36174331c |
| residual SNN processor | 87.11 | Not recorded | 695c96d653fdd5c36174331c |
| Aliyev et al. | 86.6 | Not recorded | 695c96d653fdd5c36174331c |
| SiBrain | 82.93 | Not recorded | 695c96d653fdd5c36174331c |
| E3NE | 80.6 | Not recorded | 695c96d653fdd5c36174331c |

### SCPU

Accuracy: 90.6. Result ID: 6999b4cc5698665ec42dde30.

[Reporting paper](<https://www.sota2.com/research/paper/695c96d653fdd5c36174331c.md>)

Recorded evaluation configuration: {"FPGA model":"Virtex-7","Frequency":"200 MHz","SNN model":"ResNet-11","Model depth":"11","Precision":"8 bits","LUTs":"178k","FFs":"127k"}. This record does not assert independent reproduction.

### SiBrain (High Depth)

Accuracy: 90.25. Result ID: 6999b4cc5698665ec42dde32.

[Reporting paper](<https://www.sota2.com/research/paper/695c96d653fdd5c36174331c.md>)

Recorded evaluation configuration: {"FPGA model":"Virtex-7","Frequency":"200 MHz","SNN model":"CONVNet(VGG-11)","Model depth":"11","Precision":"8 bits","Number of parameters":"9.2M","LUTs":"140k","FFs":"122k"}. This record does not assert independent reproduction.

### residual SNN processor

Accuracy: 87.11. Result ID: 6999b4cc5698665ec42dde34.

[Reporting paper](<https://www.sota2.com/research/paper/695c96d653fdd5c36174331c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695c96d653fdd5c36174331c.md>)

Recorded evaluation configuration: {"FPGA model":"ZCU216","Frequency":"100 MHz","SNN model":"ResNet-10","Model depth":"10","Precision":"8 bits","Number of parameters":"0.69M","LUTs":"135k","FFs":"342k"}. This record does not assert independent reproduction.

### Aliyev et al.

Accuracy: 86.6. Result ID: 6999b4cc5698665ec42dde33.

[Reporting paper](<https://www.sota2.com/research/paper/695c96d653fdd5c36174331c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d31e209131cea6a106.md>)

Recorded evaluation configuration: {"FPGA model":"XCVU13P","Frequency":"100 MHz","SNN model":"VGG-9","Model depth":"9","Precision":"4 bits"}. This record does not assert independent reproduction.

### SiBrain

Accuracy: 82.93. Result ID: 6999b4cc5698665ec42dde31.

[Reporting paper](<https://www.sota2.com/research/paper/695c96d653fdd5c36174331c.md>)

Recorded evaluation configuration: {"FPGA model":"Virtex-7","Frequency":"200 MHz","SNN model":"CONVNet(VGG-11)","Model depth":"6","Precision":"8 bits","Number of parameters":"0.3M","LUTs":"167k","FFs":"136k"}. This record does not assert independent reproduction.

### E3NE

Accuracy: 80.6. Result ID: 6999b4cc5698665ec42dde2f.

[Reporting paper](<https://www.sota2.com/research/paper/695c96d653fdd5c36174331c.md>)

Recorded evaluation configuration: {"FPGA model":"XCVU13P","Frequency":"150 MHz","SNN model":"AlexNet","Model depth":"8","Precision":"6 bits","LUTs":"48k","FFs":"50k"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.